MS2: Multi-Document Summarization of Medical Studies
arXiv:2104.06486
Abstract
To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and highly manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support of this goal, we release MS^2 (Multi-Document Summarization of Medical Studies), a dataset of over 470k documents and 20k summaries derived from the scientific literature. This dataset facilitates the development of systems that can assess and aggregate contradictory evidence across multiple studies, and is the first large-scale, publicly available multi-document summarization dataset in the biomedical domain. We experiment with a summarization system based on BART, with promising early results. We formulate our summarization inputs and targets in both free text and structured forms and modify a recently proposed metric to assess the quality of our system's generated summaries. Data and models are available at https://github.com/allenai/ms2
arXiv comment8 pages of content, 20 pages including references and appendix. See https://github.com/allenai/ms2/ for code, https://ai2-s2-ms2.s3-us-west-2.amazonaws.com/ms_data_2021-04-12.zip for data (1.8G, zipped) Published in EMNLP 2021 @ https://aclanthology.org/2021.emnlp-main.594/
References in corpus (11)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- BERTScore: Evaluating Text Generation with BERT
- Longformer: The Long-Document Transformer
- API design for machine learning software: experiences from the scikit-learn project
- ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
- Pretrained Language Models for Sequential Sentence Classification
- Pre-training via Paraphrasing
- Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
- Towards a Neural Network Approach to Abstractive Multi-Document Summarization
- Nutribullets Hybrid: Multi-document Health Summarization